Yeni Corona virüs hastalığının önceden eğitilmiş evrişimli sinir ağları kullanılarak göğüs röntgen görüntülerinden tespiti

Öz

COVID-19 virüsü özellikle yaşlı bireyleri ve kronik rahatsızlığı bulunan hastaları ciddi bir şekilde etkileyen ve ölümlere sebep olmaktadır. Hızlı ve doğru bir erken teşhis ölüm oranını düşürmede ve bu salgının ekonomik maliyetini azaltmada anahtar bir role sahiptir. Bu amaçla, teşhis kitleri, teşhis aletleri ve tıbbi görüntüleme kullanılarak teşhis gibi yöntemler geliştirilmiştir. Her ne kadar bunlar arasında bilgisayarlı tomografi ile elde edilen göğüs görüntüleri altın bir standart olarak kabul edilse de, bu cihaza erişimde genellikle sorun yaşanmaktadır. Bu nedenle, röntgen cihazı gibi daha kolay ulaşılabilen cihazlar yardımıyla teşhis konulması oldukça önemlidir. Kaggle tarafından sunulan ve göğüs röntgen görüntülerinden oluşan “COVID-19 radiography database” veri tabanı bu çalışmada kullanılmıştır. Üç farklı ResNet modeli (ResNet 50, ResNet 101 ve ResNet 152) (a) COVID-19 hastalarının sağlıklı bireylerden ayırt edilmesi, (b) COVID-19 hastalarının zatürre hastalarından ayırt edilmesi ve (c) COVID-19 hastalarının zatürre hastaları ve sağlıklı bireylerden ayırt edilmesi için denenmiştir. Bu modeller arasında en yüksek başarılı sonuçları ResNet 50 modeli vermiştir. Elde edilen sonuçlara göre, COVID-19 hastalarının sağlıklı bireylerden ayırt edilmesinde %99,3 başarıya, COVID-19 hastalarının zatürre hastalarından ayırt edilmesinde %99,2 başarıya ve COVID-19 hastalarının hem normal bireylerden hem de zatürre hastalarından ayırt edilmesinde %97,3 başarıya ulaştık. Bu sonuçlar bildiğimiz kadarıyla sadece röntgen görüntüleri kullanılarak COVID-19 teşhisinde elde edilen en yüksek sınıflandırıcı başarımlarıdır. Sonuç olarak, önceden eğitilmiş ResNet 50 modeli COVID-19 hastalarının sadece göğüs röntgen görüntülerinden hızlı ve doğru bir şekilde tespit edilmesinde büyük bir potansiyele sahiptir. Röntgen cihazları sağlık kuruluşlarında diğerlerine kıyasla nispeten daha kolay erişilebilir cihazlar olduğundan, bu çalışmada kullanılan modelin bu salgını yenme konusunda yardımcı olacağına inanıyoruz.

Anahtar Kelimeler

• Teşhis
• COVID-19
• Corona virüs
• Röntgen görüntüleri
• Derin öğrenme
• ResNet modelleri

Detection of new coronavirus disease from chest x-ray images using pre-trained convolutional neural networks

Öz

The COVID-19 virus has affected seriously and caused death especially for older people and patients with chronic diseases. Rapid and accurate early diagnosis has a key role to reduce the mortality and to decrease the economic cost of this pandemic. For this purpose, diagnostic kits, diagnostic aids, and diagnosis using medical imaging methods have been investigated. Although the chest imaging using Computed Tomography (CT) has been accepted as a golden standard among them, there is big challenge to reach this equipment in general. Hence, the diagnosis using more accessible devices like X-rays is very crucial. Kaggle’s chest X-ray images called the “COVID-19 radiography database” were used in this study. Three different ResNet models (ResNet 50, ResNet 101, and ResNet 152) were investigated (a) to discriminate patients with COVID-19 from normal subjects, (b) to discriminate patients with COVID-19 from patients with Pneumonia, and (c) to discriminate patients with COVID-19, patients with Pneumonia, and normal subjects. ResNet 50 model gave the highest performances among these three models. As a result, we achieved the accuracy of 99.3% to discriminate COVID-19 and Normal, the accuracy of 99.2% to discriminate COVID-19 and Pneumonia, and the accuracy of 97.3% to discriminate COVID-19, Normal, and Pneumonia. In our knowledge, these results are the highest classification accuracies in the literature in diagnosing COVID-19 using x-ray images only. In conclusion, the pre-trained ResNet 50 model has a big potential to detect the patients with COVID-19 quickly and accurately using chest X-Ray images only. Since X-ray devices are relatively more accessible devices in health organizations, we believe that the model used in this study may help defeating this pandemic.

Anahtar Kelimeler

• Diagnosis
• COVID-19
• Corona virus
• x-ray images
• deep learning
• ResNet models

Kaynakça

1. [1] Zhu N., Zhang D., Wang W., Li X., Yang B. vd., A novel coronavirus from patients with pneumonia in China, 2019, The New England Journal of Medicine, 382, 727-733, 2020.
2. [2] CDC COVID-19 Response Team, Severe outcomes among patients with coronavirus disease 2019 (COVID-19) - United States, MMWR Morb Mortal Wkly Rep 2020, https://www.cdc.gov/mmwr/volumes/69/wr/mm6912e2.htm
3. [3] World Health Organization, Coronavirus disease (COVID-19) situation report of weekly operational update. Nov 13, 2020. https://www.who.int/publications/m/item/weekly-operational-update-on-covid-19---13-november-2020
4. [4] Verma H.K., Merchant N., Verma M.K., Kuru C.I., Singh A.N. vd., Current updates on the European and WHO registered clinical trials of coronavirus disease 2019 (COVID-19), Biomedical Journal, corrected proof, 2020.
5. [5] World Health Organization, Framework for decision-making: implementation campaigns in the context of COVID-19, Interim Guidance, May 22, 2020.
6. [6] Isler Y., Discrimination of systolic and diastolic dysfunctions using multi-layer perceptron in heart rate variability analysis, Computers in Biology and Medicine, 76, 113-119, 2016.
7. [7] Badnjevic A., Gurbeta L., Custovic E., An expert diagnostic system to automatically identify asthma and chronic obstructive pulmonary disease in clinical settings, Scientific Reports, 8, 1-9, 2018.
8. [8] Zhou Z.H., Jiang Y., Yang Y.B., Chen S.F., Lung cancer cell identification based on artificial neural network ensembles, Artificial Intelligence in Medicine, 24, 25-36, 2002.

9. [9] Lin T., Yan C.R., Chen W.T., Autonomous detection of pulmonary nodules on CT images with a neural network-based fuzzy system, Computerized Medical Imaging and Graphics, 29, 447-58, 2005.
10. [10] Wang W., Xu Y., Gao R., Lu R., Han K. vd., Detection of SARS-CoV-2 in different types of clinical specimens, JAMA, 323, 1843-1844, 2020.
11. [11] Xu X., Jiang X., Ma C., Du P., Li X. vd., Deep learning system to screen coronavirus disease 2019 pneumonia, arXiv preprint, 2020. arXiv:2002.09334.
12. [12] Ardakani A.A., Kanafi A.R., Acharya U.R., Khadem N., Mohammadi A., Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks, Computers in Biology and Medicine, 121, 103795, 2020.
13. [13] Ai T., Yang Z., Hou H., Zhan C., Chen C. vd., Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: a Report of 1014 cases, Radiology, 296(2), E32-E40, 2020.
14. [14] Fang Y., Zhang H., Xie J., Lin M., Ying L. vd., Sensitivity of chest CT for COVID-19: comparison to RT-PCR, Radiology, 296(2), E115-E117, 2020.
15. [15] Chung M., Bernheim A., Mei X., Zhang N., Huang M. vd., CT imaging features of 2019 novel coronavirus (2019-nCoV), Radiology, 295(1), 202-207, 2020.
16. [16] Afshar P., Heidarian S., Naderkhani F., Oikonomou A., Plataniotis K.N., Mohammadi A., COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from x-ray images, Pattern Recognition Letters, 138, 638-643, 2020.
17. [17] Nihashi T., Ishigaki T., Satake H., Ito S., Kaii O. vd., Monitoring of fatigue in radiologists during prolonged image interpretation using fNIRS, Japanese Journal of Radiology, 37, 437-448, 2019.
18. [18] Taylor-Phillips S., Stinton C., Fatigue in radiology: a fertile area for future research, The British Journal of Radiology, 92(1099), 20190043, 2019.
19. [19] Wong H.Y.F., Lam H.Y.S., Fong A.H.T., Leung S.T., Chin T.W.Y. vd., Frequency and distribution of chest radiographic findings in COVID-19 positive patients, Radiology, 296(2), E72-E78, 2020.
20. [20] Faust O., Hagiwara Y., Hong T.J., Lih O.S., Acharya U.R., Deep learning for healthcare applications based on physiological signals: a review, Computer Methods and Programs in Biomedicine, 161, 1-13, 2018.
21. [21] Vasilakos A.V., Tang Y., Yao Y., Neural networks for computer-aided diagnosis in medicine: a review, Neurocomputing, 216, 700-708, 2016.
22. [22] Talo M., Yildirim O., Baloglu U.B., Aydin G., Acharya U.R., Convolutional neural networks for multi-class brain disease detection using MRI images, Computerized Medical Imaging and Graphics, 78, 101673, 2019.
23. [23] Zhang Y., Classification and diagnosis of thyroid carcinoma using reinforcement residual network with visual attention mechanisms in ultrasound images, Journal of Medical Systems, 43, 323, 2019.
24. [24] Szczypinski P., Klepaczko A., Pazurek M., Daniel P., Texture and color-based image segmentation and pathology detection in capsule endoscopy videos, Computer Methods and Programs in Biomedicine, 113, 396-411, 2014.
25. [25] Oh S.L., Ng E.Y., San Tan R., Acharya U.R., Automated beat-wise arrhythmia diagnosis using modified U-net on extended electrocardiographic recordings with heterogeneous arrhythmia types, Computers in Biology And Medicine, 105, 92-101, 2019.
26. [26] Falk T., Mai D., Bensch R., Cicek R., Abdulkadir A. vd., U-Net: deep learning for cell counting, detection, and morphometry, Nature Methods, 16, 67-70, 2019.
27. [27] Narin A., Isler Y., Investigation of the effect of histogram equalization method on the classifier performance of the convolutional neural network for Covid-19 chest radiography images, In 2nd International Conference of Applied Sciences, Engineering and Mathematics (IBU-ICASEM 2020), June 4-6, Skopje/North Macedonia, 2020.
28. [28] Ozturk T., Talo M., Yildirim E.A., Baloglu U.B., Yildirim O., Acharya U.R., Automated detection of COVID-19 cases using deep neural networks with X-ray images, Computers in Biology and Medicine, 121, 103792, 2020.
29. [29] Li T., Han Z., Wei B., Zheng Y., Hong Y., Cong J., Robust screening of COVID-19 from chest x-ray via discriminative cost-sensitive learning, arXiv preprint 2020, arXiv:2004.12592.
30. [30] Apostolopoulos I.D., Mpesiana T.A., Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks, Physical and Engineering Sciences in Medicine, 43, 635-640, 2020.
31. [31] Narin A, Kaya C, Pamuk Z., Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks, arXiv preprint 2020, arXiv:2003.10849.
32. [32] Wang L., Lin Z.Q., Wong A., COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images, Scientific Reports, 10, 19549, 2020.
33. [33] Sethy P.K., Behera S.K., Detection of coronavirus disease (COVID-19) based on deep features, Preprints, 2020030300, 2020.
34. [34] Chowdhury M.E.H., Rahman T., Khandakar A., Mazhar R., Kadir M.A. vd., Can AI help in screening viral and COVID-19 pneumonia?, IEEE Access, 8, 132665 -132676, 2020.
35. [35] Casistica Radiologica Italiana, COVID-19 Database, 2020. https://www.sirm.org/category/senza-categoria/covid-19/
36. [36] Cohen J.P., Morrison P., Dao L., COVID-19 image data collection, arXiv preprint, 2020. https://arxiv.org/pdf/2003.11597.pdf
37. [37] Mooney P., Chest X-Ray Images (Pneumonia), 2018. https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
38. [38] Acharya U.R., Oh S.L., Hagiwara Y., Hong Tan J., Adeli H., Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals, Computers in Biology and Medicine, 100, 270-278, 2018.
39. [39] Han D., Liu Q., Fan W., A new image classification method using CNN transfer learning and web data augmentation, Expert Systems with Applications, 95, 43-56, 2018.
40. [40] Goodfellow I., Bengio Y., Courville A., Deep Learning, MIT Press, 2016.
41. [41] Garbin C., Zhu X., Marques O., Dropout vs batch normalization: an empirical study of their impact to deep learning, Multimedia Tools and Applications, 22, 1-39, 2020.
42. [42] Krizhevsky A., Sutskever I., Hinton G.E., Imagenet classification with deep convolutional neural networks, In Advances in Neural Information Processing Systems 2012, 1097-1105, 2012.
43. [43] He K., Zhang X., Ren S., Sun J., Deep residual learning for image recognition, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, 770-778, 2016.
44. [44] Yamashita R., Nishio M., Do R.K., Togashi K., Convolutional neural networks: an overview and application in radiology, Insights into Imaging, 9, 611-629, 2018.
45. [45] Kaur T., Gandhi T.K., Deep convolutional neural networks with transfer learning for automated brain image classification, Machine Vision and Applications, 31, 1-16, 2020.
46. [46] Deng J., Dong W., Socher R., Li L.J., Li K., Fei-Fei L., Imagenet: A large-scale hierarchical image database, In 2009 IEEE Conference on Computer Vision and Pattern Recognition 2009, 248-255, 2009.
47. [47] Russakovsky O., Deng J., Su H., Krause J., Satheesh S. vd., ImageNet large scale visual recognition challenge (ILSRVC), Int J Comput Vis, 115, 211-252, 2015.
48. [48] Shorten C., Khoshgoftaar T.M., A survey on image data augmentation for deep learning, Journal of Big Data, 6, 60, 2019.
49. [49] Duda R.O., Hart P.E., Stork D.G., Pattern Classification, 2nd Edition, John Wiley and Sons, New York, 2001.
50. [50] Chicco D., Jurman G., The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation, BMC Genomics, 21, 1-6, 2020.
51. [51] Isler Y., Narin A., Ozer O., Perc M., Early prediction of paroxysmal atrial fibrillation based on short-term heart rate variability, Physica A, 509, 56-65, 2018.
52. [52] Isler Y., Narin A., Ozer O., Perc M., Multi-stage classification of congestive heart failure based on short-term heart rate variability, Chaos, Solitons & Fractals, 118, 145-151, 2019.
53. [53] Wong T., Yang N., Dependency analysis of accuracy estimates in k-fold cross validation, IEEE Transactions on Knowledge and Data Engineering, 29, 2417-2427, 2017.
54. [54] Google Colab, Colaboratory is a free Jupyter notebook environment that requires no setup and runs entirely in the cloud. https://colab.research.google.com/notebooks/welcome.ipynb
55. [55] Jouppi N.P., Young C., Patil N., Patterson D., Agrawal D. vd., In-datacenter performance analysis of a tensor processing unit, In Proceedings of the 44th Annual International Symposium on Computer Architecture, 2017 June; 1-12.
56. [56] Chollet F., Deep Learning With Python, Shelter Island, NY, USA: Manning, 2019.
57. [57] Gulli A., Pal S., Deep learning with Keras, Packt Publishing Ltd., 2017.
58. [58] Isler Y., Narin A., Ozer M., Comparison of the effects of cross-validation methods on determining performances of classifiers used in diagnosing congestive heart failure, Measurement Science Review, 15, 196-201, 2015.
59. [59] Narin A., Isler Y., Ozer M., Konjestif kalp yetmezligi teshisinde kullanilan capraz dogrulama yontemlerinin siniflandirici performanslarinin belirlenmesine olan etkilerinin karsilastirilmasi, Dokuz Eylul Universitesi Fen ve Muhendislik Dergisi, 16, 1-8, 2014.
60. [60] Cubuk E.D., Zoph B., Mane D., Vasudevan V., Le Q.V., Autoaugment: Learning augmentation strategies from data, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019, 1131-23, 2019.
61. [61] Kingma D.P., Ba J., ADAM: A method for stochastic optimization, In Proceedings of the International Conference on Learning Representations (ICLR), 2014.